# Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2502.13127 · HTML: https://mlsanity.com/paper/2502.13127/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 75 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [World Model on Million-Length Video And Language With Blockwise RingAttention](https://mlsanity.com/paper/2402.08268/) (2024)
- [Data Engineering for Scaling Language Models to 128K Context](https://mlsanity.com/paper/2402.10171/) (2024)
- [CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://mlsanity.com/paper/2305.02309/) (2023)
- [Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP](https://mlsanity.com/paper/2407.00402/) (2024)
- [Are Long-LLMs A Necessity For Long-Context Tasks?](https://mlsanity.com/paper/2405.15318/) (2024)
- [Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models](https://mlsanity.com/paper/2405.17915/) (2024)
- [Extending Llama-3's Context Ten-Fold Overnight](https://mlsanity.com/paper/2404.19553/) (2024)
- [AI Governance and Accountability: An Analysis of Anthropic's Claude](https://mlsanity.com/paper/2407.01557/) (2024)

## Built on by (most cited first, 6 of 6)

- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Unleashing Hour-Scale Video Training for Long Video-Language Understanding](https://mlsanity.com/paper/2506.05332/) (2025)
- [VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking](https://mlsanity.com/paper/2603.20185/) (2026)
- [TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://mlsanity.com/paper/2508.01473/) (2025)
- [Probing How Scalable Table Data Enhances General Long-Context Reasoning](https://mlsanity.com/paper/2603.21719/) (2026)
- [Learning to Learn from Context: Synthetic Training from Perturbed Public Documents](https://mlsanity.com/paper/2609.33642/) (2026)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond. However, simply extending the input sequence length does not necessarily lead to effective long-context understanding. In this study, we integrate Chain-of-Thought (CoT) reasoning into LLMs in a supervised manner to facilitate effective long-context understanding. To achieve this, we introduce LongFinanceQA, a synthetic dataset in the financial domain designed to improve long-context reasoning. Unlike existing long-context synthetic data, LongFinanceQA includes intermediate CoT reasoning before the final conclusion, which encourages LLMs to perform explicit reasoning, improving accuracy and interpretability in long-context understanding. To generate synthetic CoT reasoning, we propose Property-based Agentic Inference (PAI), an agentic framework that simulates human-like reasoning steps, including property extraction, retrieval, and summarization. We evaluate PAI's reasoning capabilities by assessing GPT-4o-mini w/ PAI on the Loong benchmark, outperforming standard GPT-4o-mini by 20.0%. Furthermore, we fine-tune LLaMA-3.1-8B-Instruct on LongFinanceQA, achieving a 28.0% gain on Loong's financial subset.